search

skhadem / 3D-BoundingBox

PyTorch implementation for 3D Bounding Box Estimation Using Deep Learning and Geometry
MIT License
435 stars 96 forks source link

Different outputs for same input image #29

Closed jamesheatonrdm closed 1 year ago

jamesheatonrdm commented 1 year ago

Feeding in the same image multiple times produces different orientation estimations each time. Does anyone know why this would be the case?

jamesheatonrdm commented 1 year ago

Well obviously if the model is not in eval() mode the dropout still occurs!

zzylovexx commented 1 year ago

i think it model is not stable maybe so every time the predict orientation will be different